Hey there,
Last Thursday was W8: AI-Powered Job Hunt. The series took the judgment system from W6 and the CLAUDE.md file from W7 and pointed both at the thing almost everyone in the room does badly. Finding the next role.
Most job hunts are a numbers game played badly. Skim a portal. Paste the same CV at fifty roles. Lose track of which ones. Double-apply at two of them. Hear nothing back.
The spreadsheet you keep forgetting to update is not a system. It is a guilt file. It records what you already did and shames you for not doing more.
The fix is not a better spreadsheet. It is a filter that judges, and a memory that never forgets.
The first move is mental. Stop thinking of AI as the thing that writes your cover letter. Start thinking of it as a recruiter you hired.
The first week they are useless, because they do not know you. You feed them: your CV, your story, the roles you want, the roles you would never take, the things that make a job a non-starter. Within a week they read a hundred postings for you, rank the five worth your week, flag the ghost jobs, and never forget a single one.
The whole system rests on two files. If you have been building along, you have seen both before.
cv.md is the single source of truth for who you are. Every score, every gap, every verdict reads it. You never hardcode a fact from it anywhere else.
CLAUDE.md is how you decide. Your scoring rubric, your dealbreakers, and the one guardrail that matters: the AI never auto-submits anything. It evaluates and recommends. You decide and act.
W6 made your judgment permanent. W7 made your standards permanent. W8 points both at the job hunt.
No scripted scenario. The room picked the portal. I am not a fan of it, but it was the one the room chose, so we used it. Real Python developer postings in Bangalore, dropped into a file for the evaluator to read.
It noticed on its own that the batch was Bangalore-based and flagged the lot as a high-level skip on location. It still scored them. And one posting it read differently, scored a very good match, and produced a tailored CV variant off the master CV, ready to work from.
The filter and the tailor are the same system. It tells you what to skip. For the one worth your time, it hands you a CV shaped to that role, built from your real story.
Someone asked: if the AI matches me to a job at 60 percent, how do I handle the other 40 in the interview?
A 60 percent match is not a rejection. It is a map of the gap. And the system that found the gap is the same system that helps you close it. Flashcards for the weak spots. A behavioral guide. A technical guide. Even what these companies actually ask candidates.
That is the next session. First you build the system that decides which jobs are worth you. Then you build the system that makes you worth the jobs you want.
Two things to run after W8.
First, the new W8 cheatsheet is up: the cv.md + CLAUDE.md two-file starter, the APPLY / SKIP / TAILOR decision card, and the never-auto-submit guardrail, on one page.
Second, open Claude Code in an empty folder, create cv.md with your real experience, create CLAUDE.md with your dealbreakers and the guardrail, and paste a real posting. Watch it score. That is how tonight becomes real.
The lead article from the build is also live. More coming through the week.
Reply with the role you are aiming for. I read every reply.
Talk soon,
Merryl